Simulation of SisFall Dataset for Fall Detection Using MATLAB Classifier Algorithms

Fall accidents are considered one of the significant global public health concerns, and the largest proportion of fatal accidents are experienced by elderly people aged 65 and above. Currently, there is a demand for creating an effective machine learning-based fall detection system that is significantly portable at a low cost. For development, public datasets are available to simulate an effective classifier. Hence, the current study was aimed to simulate the SisFall dataset to acquire an effective machine learning classifier for fall detection. The methodology included a study of the various fall detection systems as well as general features for machine learning classifications. The most suitable potential combination of machine learning algorithms that will provide the best accuracy, precision, sensitivity, specificity, and lowest training time was developed via simulation models using MATLAB. Input data was selected from the SisFall dataset for simulations. Up to 24 algorithms, including Decision Trees, Discriminant Analysis, Naïve Bayes, Support Vector Machines (SVM), k-Nearest Neighbors (KNN) and available Ensemble Classifiers, were simulated. Four sets of experiments were done using accelerometers with varying features and cross-validation. Currently, a combination of Cubic SVM and Fine KNN was chosen to be used as the most appropriate classifier to train a fall detection system.